AI Paper Atlas

Research map / 3D vision / Human pose estimation

Generalized Feedback Loop for Joint Hand-Object Pose Estimation

Markus Oberweger, Paul Wohlhart, Vincent Lepetit

TPAMI 2019 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 82 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add feedback loop (synthesizer + updater) to DeepPrior++ predictorDeepPrior++ · NYU hand poseaverage 3D error (mm): 12.2 mm -> 10.8 mmImproved
use learned updater instead of direct L-BFGS-B image-difference optimization (ablation)feedback loop · NYU hand poseaverage 3D error (mm): 32.3 mm vs 12.2 mm initial poseImproved
add feedback loop to hand-object predictors (ablation)hand-object pose estimator · DexterHOcombined error (mm): 19.3mm -> 17.6mmImproved
use separate CNNs for hand and object instead of a single network (ablation)hand-object pose estimator · DexterHOaverage combined error (mm): 36.6 mm -> 17.6 mmImproved
use more than two updater iterations (ablation)feedback loop · DexterHOaccuracyNo clear effect
train updater with Particle Swarm Optimization instead of L-BFGS-B for image-based fitting (ablation)image-based optimization · NYU hand poseaccuracyNo clear effect
train predictor, synthesizer and updater jointly end-to-end from pretrained init (ablation)feedback loop · NYU hand poseaccuracyNo clear effect
train updater with object synthesizer CNN instead of OpenGL renderer (ablation)feedback loop · DexterHOaccuracyNo clear effect
use stride instead of max-pooling in updater CNN (ablation)updater CNN · NYU hand poseaccuracyImproved
train object localizer on spherical objects, test on cuboids (ablation)object localizer CNN · DexterHOlocalization error (mm): 40 mm worseHurt
train hand localizer on spherical objects, test on cuboids (ablation)hand localizer CNN · DexterHOlocalization error (mm): 1 mm worseHurt
layer-wise training of synthesizer instead of end-to-end (ablation)synthesizer CNN · NYU hand posereconstruction errorImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy